KKT-Informed Neural Network

• URL: http://arxiv.org/abs/2409.09087v1
• Date: Wed, 11 Sep 2024 15:49:36 GMT
• Title: KKT-Informed Neural Network
• Authors: Carmine Delle Femine,
• Abstract summary: A neural network-based approach for solving convex optimization problems is presented. The network estimates the optimal points given a batch of input parameters. It is trained by penalizing violations of the Karush-Kuhn-Tucker conditions, ensuring its predictions adhere to these optimality criteria.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A neural network-based approach for solving parametric convex optimization problems is presented, where the network estimates the optimal points given a batch of input parameters. The network is trained by penalizing violations of the Karush-Kuhn-Tucker (KKT) conditions, ensuring that its predictions adhere to these optimality criteria. Additionally, since the bounds of the parameter space are known, training batches can be randomly generated without requiring external data. This method trades guaranteed optimality for significant improvements in speed, enabling parallel solving of a class of optimization problems.

Related papers

• Karush-Kuhn-Tucker Condition-Trained Neural Networks (KKT Nets) [0.0]
  We present a novel approach to solving convex optimization problems by leveraging the Karush-Kuhn-Tucker (KKT) conditions. Similar to Theory-Trained Neural Networks (TTNNs), the parameters of the convex optimization problem are input to the neural network. A choice for the loss function in this case is a loss, which we refer to as the KKT Loss, that measures how well the network's outputs satisfy the KKT conditions.
  arXiv  Detail & Related papers  (2024-10-21T12:59:58Z)
• A constrained optimization approach to improve robustness of neural networks [1.2338729811609355]
  We present a novel nonlinear programming-based approach to fine-tune pre-trained neural networks to improve robustness against adversarial attacks while maintaining accuracy on clean data.
  arXiv  Detail & Related papers  (2024-09-18T18:37:14Z)
• RoPINN: Region Optimized Physics-Informed Neural Networks [66.38369833561039]
  Physics-informed neural networks (PINNs) have been widely applied to solve partial differential equations (PDEs) This paper proposes and theoretically studies a new training paradigm as region optimization. A practical training algorithm, Region Optimized PINN (RoPINN), is seamlessly derived from this new paradigm.
  arXiv  Detail & Related papers  (2024-05-23T09:45:57Z)
• End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty [55.04219793298687]
  The Predict-Then-Forecast (PtO) paradigm in machine learning aims to maximize downstream decision quality. This paper extends the PtO methodology to optimization problems with nondifferentiable Ordered Weighted Averaging (OWA) objectives. It shows how optimization of OWA functions can be effectively integrated with parametric prediction for fair and robust optimization under uncertainty.
  arXiv  Detail & Related papers  (2024-02-12T16:33:35Z)
• Optimal Sets and Solution Paths of ReLU Networks [56.40911684005949]
  We develop an analytical framework to characterize the set of optimal ReLU networks. We establish conditions for the neuralization of ReLU networks to be continuous, and develop sensitivity results for ReLU networks.
  arXiv  Detail & Related papers  (2023-05-31T18:48:16Z)
• Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems [62.83783246648714]
  We propose a sequential quadratic programming algorithm (TR-StoSQP) to solve nonlinear optimization problems with objectives and deterministic equality constraints. The algorithm adaptively selects the trust-region radius and, compared to the existing line-search StoSQP schemes, allows us to utilize indefinite Hessian matrices.
  arXiv  Detail & Related papers  (2022-11-29T05:52:17Z)
• AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks [12.229154524476405]
  We develop a new algorithm, Annealed Skewed SGD - AskewSGD - for training deep neural networks (DNNs) with quantized weights. Unlike algorithms with active sets and feasible directions, AskewSGD avoids projections or optimization under the entire feasible set. Experimental results show that the AskewSGD algorithm performs better than or on par with state of the art methods in classical benchmarks.
  arXiv  Detail & Related papers  (2022-11-07T18:13:44Z)
• Implicit Rate-Constrained Optimization of Non-decomposable Objectives [37.43791617018009]
  We consider a family of constrained optimization problems arising in machine learning. Our key idea is to formulate a rate-constrained optimization that expresses the threshold parameter as a function of the model parameters. We show how the resulting optimization problem can be solved using standard gradient based methods.
  arXiv  Detail & Related papers  (2021-07-23T00:04:39Z)
• Convergence of adaptive algorithms for weakly convex constrained optimization [59.36386973876765]
  We prove the $mathcaltilde O(t-1/4)$ rate of convergence for the norm of the gradient of Moreau envelope. Our analysis works with mini-batch size of $1$, constant first and second order moment parameters, and possibly smooth optimization domains.
  arXiv  Detail & Related papers  (2020-06-11T17:43:19Z)
• The Hidden Convex Optimization Landscape of Two-Layer ReLU Neural Networks: an Exact Characterization of the Optimal Solutions [51.60996023961886]
  We prove that finding all globally optimal two-layer ReLU neural networks can be performed by solving a convex optimization program with cone constraints. Our analysis is novel, characterizes all optimal solutions, and does not leverage duality-based analysis which was recently used to lift neural network training into convex spaces.
  arXiv  Detail & Related papers  (2020-06-10T15:38:30Z)
• An Outer-approximation Guided Optimization Approach for Constrained Neural Network Inverse Problems [0.0]
  constrained neural network inverse problems refer to an optimization problem to find the best set of input values of a given trained neural network. This paper analyzes the characteristics of optimal solutions of neural network inverse problems with rectified activation units. Experiments demonstrate the superiority of the proposed algorithm compared to a projected gradient method.
  arXiv  Detail & Related papers  (2020-02-24T17:49:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.